PHP使用QueryList抓取BSC合约交易Table

环境说明

• TP6
• PHP 8.0
• QueryList 4.2.8

步骤说明

需求

采集www.bscscan.com中交易信息

安装 QueryList

composer require jaeger/querylist

代码示例

class Bsc
{
    
    private function getSid($html)
    {
        $html = strstr($html, 'var sid =');
        $html = substr($html, strpos($html, 'var sid = \'') + 11);
        return substr($html, 0, strpos($html, "'"));
    }

    private function getPageData($page)
    {
        $otherArgs = [
            'headers' => [
                'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
            ],
        ];
    
        $tokenUrl = 'https://www.bscscan.com/token/' . $this->contractaddress;
        $tokenQl  = QueryList::get($tokenUrl, null, $otherArgs);
    
        $sid = $this->getSid($tokenQl->getHtml());
    
        $url = 'https://www.bscscan.com/token/generic-tokentxns2?m=normal&contractAddress=' . $this->contractaddress . '&a=&sid=' . $sid . '&p=' . $page;
        $ql  = QueryList::get($url, null, $otherArgs);
    
        // 采集交易总条数
        $total = $ql->find('.mb-4 p')->text();
    
        // 采集表格
        $table = $ql->find('table');
        // 采集表头
        $tableHeader = $table->find('tr:eq(0)')->find('th')->texts();
        // 采集表的每行内容
        $tableRows = $table->find('tr:gt(0)')->map(function ($row) {
            return $row->find('td')->texts()->all();
        });
    
        // 采集表的每行Method
        $methodsObject = $table->find('tr:gt(0)')->map(function ($row) {
            return $row->find('td .u-label')->attr('title');
        });
        $methods       = $methodsObject->all();
    
        $insertData = $tableRows->all();
        foreach ($insertData as $key => &$item) {
            $item[] = $methods[$key];
            foreach ($item as $itemKey => &$itemVal) {
                // 交易时间
                if ($itemKey == 2) {
                    $itemVal = strtotime($itemVal);
                }
                // 垃圾数据
                if ($itemKey == 1 || $itemKey == 3 || $itemKey == 5) unset($item[$itemKey]);
            }
        }
    
        $res = [];
        foreach ($insertData as $items) {
            $temp                = [
                'txn_hash' => $items[0],
                'method'   => $items[8],
                'from'     => $items[4],
                'to'       => $items[6],
                'quantity' => $items[7],
                'created'  => $items[2],
            ];
            $temp['unique_hash'] = hash('sha256', json_encode($temp));
            $res[] = $temp;
            unset($temp);
        }
        unset($insertData);
    
        return $res;
    }
}